FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376607989> ?p ?o ?g. }

• W4376607989 endingPage "2866" @default.
• W4376607989 startingPage "2857" @default.
• W4376607989 abstract "The goal of dynamic scene deblurring is to remove the motion blur presented in a given image. To recover the details from the severe blurs, conventional convolutional neural networks (CNNs) based methods typically increase the number of convolution layers, kernel-size, or different scale images to enlarge the receptive field. However, these methods neglect the non-uniform nature of blurs, and cannot extract varied local and global information. Unlike the CNNs-based methods, we propose a Transformer-based model for image deblurring, named SharpFormer, that directly learns long-range dependencies via a novel Transformer module to overcome large blur variations. Transformer is good at learning global information but is poor at capturing local information. To overcome this issue, we design a novel Locality preserving Transformer (LTransformer) block to integrate sufficient local information into global features. In addition, to effectively apply LTransformer to the medium-resolution features, a hybrid block is introduced to capture intermediate mixed features. Furthermore, we use a dynamic convolution (DyConv) block, which aggregates multiple parallel convolution kernels to handle the non-uniform blur of inputs. We leverage a powerful two-stage attentive framework composed of the above blocks to learn the global, hybrid, and local features effectively. Extensive experiments on the GoPro and REDS datasets show that the proposed SharpFormer performs favourably against the state-of-the-art methods in blurred image restoration." @default.
• W4376607989 created "2023-05-17" @default.
• W4376607989 creator A5011047259 @default.
• W4376607989 creator A5042769332 @default.
• W4376607989 creator A5054036938 @default.
• W4376607989 creator A5072326285 @default.
• W4376607989 creator A5081607584 @default.
• W4376607989 creator A5091947234 @default.
• W4376607989 date "2023-01-01" @default.
• W4376607989 modified "2023-10-13" @default.
• W4376607989 title "SharpFormer: Learning Local Feature Preserving Global Representations for Image Deblurring" @default.
• W4376607989 cites W1916935112 @default.
• W4376607989 cites W1987075379 @default.
• W4376607989 cites W2043529138 @default.
• W4376607989 cites W2103913786 @default.
• W4376607989 cites W2118456997 @default.
• W4376607989 cites W2132244934 @default.
• W4376607989 cites W2138204001 @default.
• W4376607989 cites W2141115311 @default.
• W4376607989 cites W2167307343 @default.
• W4376607989 cites W2300657047 @default.
• W4376607989 cites W2472069500 @default.
• W4376607989 cites W2474628748 @default.
• W4376607989 cites W2560533888 @default.
• W4376607989 cites W2564023417 @default.
• W4376607989 cites W2776707568 @default.
• W4376607989 cites W2798735168 @default.
• W4376607989 cites W2953823547 @default.
• W4376607989 cites W2961218591 @default.
• W4376607989 cites W2963312584 @default.
• W4376607989 cites W2964030969 @default.
• W4376607989 cites W2965217508 @default.
• W4376607989 cites W2997058852 @default.
• W4376607989 cites W3034421924 @default.
• W4376607989 cites W3034789174 @default.
• W4376607989 cites W3096609285 @default.
• W4376607989 cites W3100594395 @default.
• W4376607989 cites W3107405705 @default.
• W4376607989 cites W3131500599 @default.
• W4376607989 cites W3138516171 @default.
• W4376607989 cites W3170697543 @default.
• W4376607989 cites W3175634226 @default.
• W4376607989 cites W3176096490 @default.
• W4376607989 cites W3202040256 @default.
• W4376607989 cites W3207918547 @default.
• W4376607989 cites W4214815024 @default.
• W4376607989 cites W4225672218 @default.
• W4376607989 cites W4292829074 @default.
• W4376607989 cites W4304086149 @default.
• W4376607989 cites W4312812783 @default.
• W4376607989 cites W4312914040 @default.
• W4376607989 doi "https://doi.org/10.1109/tip.2023.3251029" @default.
• W4376607989 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37186531" @default.
• W4376607989 hasPublicationYear "2023" @default.
• W4376607989 type Work @default.
• W4376607989 citedByCount "1" @default.
• W4376607989 countsByYear W43766079892023 @default.
• W4376607989 crossrefType "journal-article" @default.
• W4376607989 hasAuthorship W4376607989A5011047259 @default.
• W4376607989 hasAuthorship W4376607989A5042769332 @default.
• W4376607989 hasAuthorship W4376607989A5054036938 @default.
• W4376607989 hasAuthorship W4376607989A5072326285 @default.
• W4376607989 hasAuthorship W4376607989A5081607584 @default.
• W4376607989 hasAuthorship W4376607989A5091947234 @default.
• W4376607989 hasConcept C106430172 @default.
• W4376607989 hasConcept C114614502 @default.
• W4376607989 hasConcept C115961682 @default.
• W4376607989 hasConcept C138885662 @default.
• W4376607989 hasConcept C153083717 @default.
• W4376607989 hasConcept C153180895 @default.
• W4376607989 hasConcept C154945302 @default.
• W4376607989 hasConcept C2777693668 @default.
• W4376607989 hasConcept C2779808786 @default.
• W4376607989 hasConcept C31972630 @default.
• W4376607989 hasConcept C33923547 @default.
• W4376607989 hasConcept C41008148 @default.
• W4376607989 hasConcept C41895202 @default.
• W4376607989 hasConcept C74193536 @default.
• W4376607989 hasConcept C81363708 @default.
• W4376607989 hasConcept C9417928 @default.
• W4376607989 hasConceptScore W4376607989C106430172 @default.
• W4376607989 hasConceptScore W4376607989C114614502 @default.
• W4376607989 hasConceptScore W4376607989C115961682 @default.
• W4376607989 hasConceptScore W4376607989C138885662 @default.
• W4376607989 hasConceptScore W4376607989C153083717 @default.
• W4376607989 hasConceptScore W4376607989C153180895 @default.
• W4376607989 hasConceptScore W4376607989C154945302 @default.
• W4376607989 hasConceptScore W4376607989C2777693668 @default.
• W4376607989 hasConceptScore W4376607989C2779808786 @default.
• W4376607989 hasConceptScore W4376607989C31972630 @default.
• W4376607989 hasConceptScore W4376607989C33923547 @default.
• W4376607989 hasConceptScore W4376607989C41008148 @default.
• W4376607989 hasConceptScore W4376607989C41895202 @default.
• W4376607989 hasConceptScore W4376607989C74193536 @default.
• W4376607989 hasConceptScore W4376607989C81363708 @default.
• W4376607989 hasConceptScore W4376607989C9417928 @default.
• W4376607989 hasFunder F4320321001 @default.
• W4376607989 hasFunder F4320335787 @default.

• next